用3D CNN和蜂巢图编码提升对抗攻击下的DDoS检测准确率
Robust DDoS-Attack Classification with 3D CNNs Against Adversarial Methods
- 将网络流量转为时空蜂巢图，用3D CNN识别攻击模式
- 对抗训练使攻击样本准确率从50%提升至93%以上
- 前3-4帧即可预警，适合实时防御场景
分布式拒绝服务（DDoS）攻击持续威胁在线基础设施，常通过细微流量变化绕过检测。本文提出一种基于蜂巢图序列与3D卷积神经网络（3D CNN）的检测方法，核心思想包括：（1）利用时空蜂巢图编码建立模式识别基线；（2）结合FGSM、PGD对抗训练及空间噪声与图像平移增强鲁棒性；（3）分析帧级预测以捕捉早期信号。在基准数据集上，该方法将对抗样本准确率从50-55%提升至93%以上，同时保持对正常样本的良好性能。第3-4帧即呈现强预测信号，表明早期分类可行。
原文摘要 · Abstract (English)
Distributed Denial-of-Service (DDoS) attacks remain a serious threat to online infrastructure, often bypassing detection by altering traffic in subtle ways. We present a method using hive-plot sequences of network data and a 3D convolutional neural network (3D CNN) to classify DDoS traffic with high accuracy. Our system relies on three main ideas: (1) using spatio-temporal hive-plot encodings to set a pattern-recognition baseline, (2) applying adversarial training with FGSM and PGD alongside spatial noise and image shifts, and (3) analyzing frame-wise predictions to find early signals. On a benchmark dataset, our method lifts adversarial accuracy from 50-55% to over 93% while maintaining clean-sample performance. Frames 3-4 offer strong predictive signals, showing early-stage classification is possible.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。